From 19c86521f51c159dd2ba4b835a30d25d4df9ef82 Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Mon, 18 Mar 2024 00:17:16 +0100 Subject: [PATCH] Update README.md --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 0567e36..a955e60 100644 --- a/README.md +++ b/README.md @@ -32,7 +32,9 @@ If the intensity is set at 0 the token's normalization is still into effect. Set Both directions offer valid variations no matter the subject. -For general use I recommand "forward" at 0.3 or "backward" at 0.5~1. +For general use I recommand forward or backward at 0.5~1 for the positive prompt and to "stay in place" for the negative. + +Overall normalizing the tokens magnitudes at their mean seems to have a positive effect too. Especially with the negative prompt which tends to lower my ratio of burned images. ## Conditioning (Slerp) and Conditioning (Average keep magnitude):